INDEX

Explanations

code and email addresses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esis

-0.31

èĪį

-0.29

æīĵäºĨ

-0.27

è·Łè¸ª

-0.26

 arbit

-0.26

éĺ»åĬĽ

-0.26

 conf

-0.25

ELY

-0.25

imations

-0.25

 tracking

-0.25

POSITIVE LOGITS

loud

0.27

adden

0.26

 Notre

0.25

(coder

0.24

 Werner

0.24

hood

0.23

ordering

0.23

ëĵľë¦¬

0.23

äººéĥ½

0.23

 fread

0.23

Activations Density 0.001%

code and email addresses

No Comments

No Known Activations