INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

á»ģn

-0.28

_slices

-0.28

ITAL

-0.27

åī§çĥĪ

-0.25

.rl

-0.25

æ¿ĢçĥĪ

-0.25

å°ıæĹ¶åīį

-0.24

åĤ¥

-0.24

å¹ħ

-0.24

Gio

-0.24

POSITIVE LOGITS

stead

0.26

å¤ĦçĲĨ

0.26

elper

0.25

ica

0.25

enschaft

0.24

(Mod

0.23

iej

0.23

åı¤

0.23

 Drive

0.23

æĢĿæĥ³

0.23

Activations Density 26.504%

No Known Activations

This feature has no known activations.