INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åļ¼

-0.30

histor

-0.27

opensource

-0.26

çļĦé«ĺåº¦

-0.26

hit

-0.25

å®£åĳĬ

-0.25

 worn

-0.25

_global

-0.25

 Global

-0.25

hot

-0.24

POSITIVE LOGITS

 gamm

0.27

bird

0.27

ivre

0.25

leccion

0.24

bond

0.24

Pow

0.24

toy

0.24

]|[

0.24

iver

0.23

adic

0.23

Activations Density 0.094%

No Known Activations

This feature has no known activations.