INDEX

Explanations

code, URLs, and forum text

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

å¼±

-0.31

ering

-0.28

åİļåİļ

-0.27

aby

-0.26

èĥ¯

-0.26

ä¹ĭéģĵ

-0.25

ework

-0.25

ëł¨

-0.25

ents

-0.25

rom

-0.24

POSITIVE LOGITS

çķĶ

0.26

ç§į

0.25

YE

0.25

 organizers

0.24

sheets

0.24

VERS

0.24

 replicas

0.24

ãĥ£

0.24

åĲ¦

0.24

 NONINFRINGEMENT

0.24

Activations Density 0.007%

code, URLs, and forum text

No Comments

No Known Activations