INDEX

Explanations

bridge

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

éĻĲæľŁ

-0.30

éĢłçº¸

-0.30

oram

-0.30

ibel

-0.27

(""

-0.26

/mp

-0.25

ÑģÑĤÑĢÐ°

-0.25

?type

-0.24

itar

-0.24

mf

-0.24

POSITIVE LOGITS

ivity

0.34

ivities

0.34

æĪĳæīį

0.27

Rey

0.26

IVITY

0.26

Pot

0.26

coli

0.25

chio

0.25

enci

0.24

cepts

0.24

Activations Density 0.004%

bridge

No Comments

No Known Activations