INDEX

Explanations

source code

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

å®¹

-0.28

ablo

-0.27

cap

-0.27

åĩºå¢ĥ

-0.27

æĪª

-0.26

 comfort

-0.25

 xlabel

-0.25

cap

-0.25

éĽĨ

-0.24

åľ¨çº¿

-0.24

POSITIVE LOGITS

Og

0.31

åİŁåīĩ

0.28

æŃ£åĵģ

0.27

AAF

0.27

otent

0.25

.hits

0.25

riendly

0.25

OfWork

0.25

 KaÅ¼dy

0.25

odef

0.24

Activations Density 0.007%

source code

No Comments

No Known Activations