INDEX

Explanations

Formal writing/code fragments

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

-fw

-0.26

ÐµÑħ

-0.26

HR

-0.26

æ²ĥå°Ķ

-0.25

ç§ĴéĴŁ

-0.25

èĽ®

-0.25

è¢«è¿«

-0.25

Ð±ÑĥÑĢ

-0.25

elm

-0.24

ennon

-0.24

POSITIVE LOGITS

èĬĤ

0.31

urn

0.30

åī²

0.27

shield

0.25

lier

0.25

 Limit

0.25

asil

0.24

ÑģÑĤÑĥÐ¿

0.24

osomal

0.24

Limit

0.24

Activations Density 0.001%

Formal writing/code fragments

No Comments

No Known Activations