INDEX

Explanations

fires

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

Friendly

-0.28

æĬ¥éĶĢ

-0.27

 following

-0.27

 perfect

-0.26

following

-0.25

ÃŃcio

-0.25

:relative

-0.25

,left

-0.25

mol

-0.24

Mol

-0.24

POSITIVE LOGITS

units

0.28

å®ŀè´¨

0.27

 organisation

0.27

èĺ¸

0.27

istes

0.25

anson

0.25

(_,

0.25

 fora

0.25

nze

0.24

ç¬¬ä¸Ģå®¶

0.24

Activations Density 0.004%

fires

No Comments

No Known Activations