INDEX

Explanations

say "c or p word"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

æĬ¹

-0.30

èİ«æĸ¯

-0.25

lim

-0.24

 projection

-0.24

sci

-0.24

grab

-0.23

 Hoff

-0.23

tek

-0.23

 forc

-0.23

athy

-0.23

POSITIVE LOGITS

ç¸¾

0.37

åĵ¡

0.32

åĳ

0.29

ä¸ºç©º

0.28

ç»©

0.24

band

0.24

iture

0.24

åłĨ

0.24

imer

0.23

 pháº©m

0.23

Activations Density 0.032%

say "c or p word"

No Comments

No Known Activations