INDEX

Explanations

system

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sscanf

-0.30

å±ŀäºİèĩªå·±

-0.26

 peru

-0.26

Å¡ÃŃ

-0.26

ifix

-0.25

fts

-0.25

ftype

-0.24

Ĳľ

-0.24

 Decoration

-0.24

æĹıèĩªæ²»

-0.24

POSITIVE LOGITS

mand

0.35

 variable

0.27

ary

0.26

 manufacturer

0.26

/method

0.26

 including

0.25

 known

0.25

 betrayed

0.25

 bulletin

0.25

 adher

0.25

Activations Density 1.141%

system

No Comments

No Known Activations