INDEX

Explanations

specific strings

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ibo

-0.30

izzer

-0.26

worthy

-0.26

 ÐºÐ°ÑĤÐ°Ð»

-0.26

oji

-0.26

ran

-0.26

ItemId

-0.25

!";č↵

-0.25

_symbols

-0.24

okus

-0.24

POSITIVE LOGITS

å¡«

0.28

 precision

0.26

_precision

0.25

å¥Ĺ

0.24

GetName

0.24

éĴī

0.24

è´´

0.24

emption

0.24

SetName

0.23

åĨ»

0.23

Activations Density 0.005%

specific strings

No Comments

No Known Activations