INDEX

Explanations

hyphen

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

thouse

-0.27

çº§

-0.27

çŃĸ

-0.26

umbs

-0.26

 preload

-0.26

.po

-0.25

upe

-0.24

ç´ļ

-0.24

 dimensional

-0.24

 assessment

-0.24

POSITIVE LOGITS

ymoon

0.31

ÐµÐ³Ð¸ÑģÑĤ

0.28

åħ³åı£

0.25

æīŃ

0.24

acam

0.24

åħ³éĶ®æĹ¶åĪ»

0.24

åĨįè§ģ

0.24

æĢİä¹Īçľĭ

0.23

critical

0.23

olutely

0.23

Activations Density 0.002%

hyphen

No Comments

No Known Activations