INDEX

Explanations

door/doors

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

thr

-0.28

arp

-0.25

 Bundy

-0.25

 Ð·Ð°Ð±

-0.25

åĪĨè¾¨

-0.25

å´Ń

-0.24

åĿ¨

-0.24

amins

-0.24

egl

-0.24

æĭĩ

-0.24

POSITIVE LOGITS

ØµÙĪÙĦ

0.27

nement

0.27

 success

0.27

è¿ĺæĥ³

0.25

 perse

0.25

_LOADED

0.25

ceeded

0.24

UIT

0.24

kur

0.24

ward

0.24

Activations Density 0.784%

door/doors

No Comments

No Known Activations