INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

íĥĦ

-0.28

 tráº§m

-0.27

_modal

-0.27

_MODAL

-0.26

 Modal

-0.26

ugi

-0.26

 spons

-0.25

pite

-0.25

enderror

-0.25

 fieldValue

-0.25

POSITIVE LOGITS

fork

0.28

çļĦåľ°æĸ¹

0.26

 licked

0.25

rios

0.25

evenodd

0.25

ado

0.25

view

0.24

å¹¶åıĳ

0.24

 fork

0.24

onclick

0.24

Activations Density 0.324%

No Known Activations

This feature has no known activations.