INDEX

Explanations

model

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ento

-0.31

oyo

-0.29

chet

-0.29

culos

-0.27

resent

-0.26

erate

-0.26

ãĤ±ãĥ¼ãĤ¹

-0.25

ple

-0.24

ible

-0.24

uta

-0.24

POSITIVE LOGITS

æľªç»ıæİĪæĿĥ

0.29

 authorized

0.28

igned

0.26

åĪĨéħį

0.26

ĥģ

0.26

 Montgomery

0.26

authorized

0.26

 authorization

0.26

é£İéĽ¨

0.25

è¯ķè¡Į

0.25

Activations Density 0.049%

model

No Comments

No Known Activations