INDEX

Explanations

walking

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

æ³ķåĪĻ

-0.28

ÑģÑĤÐµ

-0.26

çĦ¦çĤ¹

-0.24

aldi

-0.24

 AppRoutingModule

-0.24

 principalTable

-0.24

ç®Ķ

-0.23

Blood

-0.23

hek

-0.23

ocus

-0.23

POSITIVE LOGITS

oling

0.30

èĮ¬

0.27

versed

0.27

Verse

0.27

isiert

0.26

CLICK

0.26

ä¸Ĭåįĩ

0.26

 towers

0.26

 Verse

0.25

verse

0.24

Activations Density 0.001%

walking

No Comments

No Known Activations