INDEX

Explanations

Technical and scientific writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çī¹å¾ģ

-0.44

 trait

-0.35

 features

-0.34

 traits

-0.32

 characteristics

-0.31

çī¹æĢ§

-0.30

features

-0.28

 feature

-0.28

 Ã¶zellik

-0.28

_feature

-0.28

POSITIVE LOGITS

edException

0.31

ards

0.28

thin

0.28

odes

0.28

sters

0.27

ç©·

0.26

å¤§åĨĽ

0.25

ErrorHandler

0.25

ä¸Ĭæ¦ľ

0.25

 Vaughan

0.25

Activations Density 0.067%

Technical and scientific writing

No Comments

No Known Activations