INDEX

Explanations

addressing problems/responses

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

>Show

-0.28

rated

-0.26

cue

-0.26

æ½²

-0.26

çĦ¦

-0.25

alom

-0.25

 bleach

-0.24

çº¿ç´¢

-0.23

 Cascade

-0.23

astically

-0.23

POSITIVE LOGITS

èĦı

0.25

DEST

0.24

idis

0.24

_dest

0.23

æĪĳè¯´

0.23

åĭŁ

0.23

æĲı

0.23

éķ«

0.23

dest

0.23

acus

0.23

Activations Density 0.002%

addressing problems/responses

No Comments

No Known Activations