INDEX

Explanations

text snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

acs

-0.29

ter

-0.26

nÄ±

-0.25

_TER

-0.25

FI

-0.25

dess

-0.25

gly

-0.24

å²Ĺ

-0.24

cai

-0.24

ASE

-0.23

POSITIVE LOGITS

åĩĢèµĦäº§

0.28

æĦıä¹īä¸ĬçļĦ

0.26

ForMember

0.26

åįķèº«

0.26

æĪĲéķ¿

0.25

oppel

0.25

enuine

0.25

olith

0.24

æĮ½

0.24

[]{

0.24

Activations Density 0.903%

text snippets

No Known Activations