INDEX

Explanations

ko

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

è½®å»ĵ

-0.26

RuleContext

-0.25

 Assembly

-0.25

 closure

-0.24

closure

-0.24

éĻĪè¿°

-0.24

[mid

-0.23

æĭĽå¾ħ

-0.23

 nothing

-0.23

pike

-0.23

POSITIVE LOGITS

osex

0.27

vo

0.26

èĻ¬

0.25

itized

0.25

sez

0.25

å¾ī

0.25

æĢ»åħ±

0.24

 getC

0.24

 Trek

0.23

rap

0.23

Activations Density 0.002%

ko

No Comments

No Known Activations