INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rice

-0.27

dent

-0.26

aped

-0.26

åĪĨæĺİ

-0.26

åĨĴ

-0.25

obic

-0.25

atis

-0.24

lier

-0.24

oice

-0.24

icious

-0.24

POSITIVE LOGITS

-shadow

0.28

inan

0.26

igers

0.25

æ¶¯

0.24

ìłķë³´

0.24

æĭįæĭį

0.24

 Ð¿ÑĢÐ¾Ð²ÐµÐ´ÐµÐ½

0.23

ABL

0.23

abcdefgh

0.23

ê²¬

0.23

Activations Density 45.820%

No Known Activations

This feature has no known activations.