INDEX

Explanations

Events, situations, reports

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enburg

-0.25

ROP

-0.25

 trailing

-0.24

along

-0.24

ä¸įä¿¡

-0.24

CR

-0.24

odge

-0.24

 where

-0.23

_pass

-0.23

POSITIVE LOGITS

stro

0.28

uchos

0.26

åĮ»åĬ¡

0.26

llu

0.25

isode

0.25

ooth

0.25

neh

0.25

posables

0.25

dde

0.25

ishly

0.25

Activations Density 0.002%

Events, situations, reports

No Comments

No Known Activations