INDEX

Explanations

from

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

_ATT

-0.27

orate

-0.27

ä¸Ģå¼Ģå§ĭå°±

-0.26

Ä±z

-0.26

è½¯

-0.25

è¯¦

-0.25

iele

-0.24

 tested

-0.24

 bombed

-0.24

jection

-0.24

POSITIVE LOGITS

cle

0.29

reso

0.27

çº³åħ¥

0.25

åħ³éĹ¨

0.25

]+)/

0.24

å·¨äºº

0.24

ÅĽcie

0.24

DC

0.24

["+

0.23

angen

0.23

Activations Density 0.010%

from

No Comments

No Known Activations